|
|
Reversibility of Voice Change Methods
Lička, Zbyněk ; Firc, Anton (oponent) ; Malinka, Kamil (vedoucí práce)
State-of-the-art voice-changing methods allow inexperienced users to create convincing voice recordings of famous individuals with just a few seconds of recorded speech. There are two major approaches to voice generation: voice conversion and text-to-speech. Voice conversion methods require the user to input source speech to be converted to the target voice. A trend with voice conversion methods, especially those requiring only mere seconds of reference speech, has been restricting the amount of information about the original speaker in the converted speech. This work focuses on studying the amount of information extractable about the original speaker from artificial speech and potentially reconstructing the original speech. The results of this work shed light on an unstudied property of voice-changing methods.
|
|
|
Raising Users' Security Awareness of Deepfakes Attacks
Novák, David ; Šalko, Milan (oponent) ; Malinka, Kamil (vedoucí práce)
This thesis provides a general overview of deepfakes, what they are, how they may be used or misused, and an introduction to cybersecurity education, especially concerning deepfakes attacks. The thesis aims to provide a way for users to enhance their awareness of security issues related to deepfake attacks. The work represents my design and implementation of a web-based application pursuing this aim, based on the summary of research concerning deepfakes. The solution offers users options to both learn about deepfakes and experience the creation of deepfakes in a simplified way. The testing of users before and after experiencing my platform indicated an increase in users' knowledge by up to 85.9\,\%. The data indicate both general user inexperience and a lack of understanding of deepfakes, which is problematic in today's trend to use deepfakes for cyber-attacks. However, based on the results, my application can fill this gap in crucial security knowledge.
|
|
|
Lámání hesel pomocí Rainbow Tables na GPU
Jahoda, David ; Holop, Patrik (oponent) ; Malinka, Kamil (vedoucí práce)
Práce se zabývá návrhem a řešením nástroje pro lámání hesel pomocí Rainbow tables za využití GPU akcelerace. Důraz je kladen výkon nástroje, použití soudobých softwarových i hardwarových prostředků. V experimentální části se pak zabývá porovnáním s dosavadními řešeními využívající Rainbow tables a účinnost protiopatření vůči nim.
|
|
|
Support Tools for Verifying Human Ability to Detect Deepfakes
Potančok, Patrik ; Malinka, Kamil (oponent) ; Firc, Anton (vedoucí práce)
The aim of this thesis is to create a web application using PHP and MySQL, that will test the human ability to detect deepfake recordings while collecting their data like date of birth, native language, proficiency in other languages, how many times and how long did they listen to a recording and a number of correct answers. This application includes management of the recordings and the users and the ability to export user data in CSV format. The application was implemented using Laravel, Vue.js and MySQL.
|
|
|
Vyhodnocení kvality a dostupnosti zdrojů obrazových médií pro tvorbu deepfakes
Andrýsek, Kryštof ; Malinka, Kamil (oponent) ; Firc, Anton (vedoucí práce)
Umělá inteligence je v posledních letech na vzestupu a začíná se stávat běžnou součástí našich životů. Tato práce se zaměřuje na nebezpečí související s obrazovými deepfakes. V současnosti se totiž ukazuje, že se netýká pouze vysoce postavených politických osobností nebo hollywoodských hvězd, ale může ovlivnit život kohokoliv z nás. K tomu přispívá mimo jiné zvyšující se množství aplikací, s jejichž pomocí dokáže deepfake vytvořit i člověk bez odborných znalostí a zkušeností. Primárním úkolem této práce je vyhodnotit zdroje, které lze využít k získání obrazových médií vhodných pro tvorbu obličejových deepfakes, a navrhnout metody, pomocí nichž je možné zhodnotit kvalitu těchto zdrojů z pohledu vhodnosti pro tvorbu deepfakes. Další cíl představuje identifikace skupin lidí, jimž hrozí vyšší riziko v souvislosti s obrazovými deepfakes, což může napomoci dokonalejší prevenci a obecnému prohloubení znalostí. Práce nabízí rozbor zdrojů použitelných k tvorbě obličejových deepfakes, navrhuje metody hodnocení jejich kvality, detailní vyhodnocení zdrojů pomocí těchto metod a analýzu zranitelnosti jednotlivých skupin osob. Nakonec je pomocí dotazníkového šetření, zaměřeného především na zdroj sociální sítě, zkoumáno, v jakém množství a jaký druh fotografií sdílejí běžní uživatelé nejčastěji, a na základě těchto údajů jsou upřesněny informace o rizikových skupinách.
|
|
|
Performance Comparison of Libraries for Homomorphic Cryptography
Babjak, Pavol ; Tamaškovič, Marek (oponent) ; Malinka, Kamil (vedoucí práce)
Cryptography is an integral part of computer security. When using common cryptographic methods and operations on them, individual data are not protected against unauthorized access or theft by third parties in any way. Homomorphic cryptography solves exactly the given problem, i.e. it can work with data containing unknown content and simultaneously perform operations on them. The goal of this thesis is to perform a set of tests to compare the performance and other important aspects of running different computational operations by different frameworks implementing homomorfic encryption of various schemes to choose the most favorable framework for certain type of operations.
|
|
|
Application for Detection of Fake News
Zádrapa, Jan ; Holop, Patrik (oponent) ; Malinka, Kamil (vedoucí práce)
The problem of Fake News is one of the most significant problems in our modern society. Millions of people read Fake News articles every day without knowing it. This problem creates a risk worldwide as society is getting polarised, and elections are manipulated by third parties using propaganda. Unfortunately, there are not enough tools to help solve the problem of Fake News detection in the Czech language. This thesis aims to create a tool to help these people recognise Fake News and introduce them commonly used manipulation techniques in text.
|
|
|
Resilience of Biometric Authentication of Voice Assistants Against Deepfakes
Kaška, Petr ; Pleško, Filip (oponent) ; Malinka, Kamil (vedoucí práce)
Voice assistants (Apple Siri, Amazon Alexa, Google-assistant, Samsung Bixby) supporting voice control offer more and more possibilities to make all our daily activities easier. People give them access to data and information to take full advantage of all these features. Along with the rapidly developing voice deepfake technology, there is a big threat in the area of misusing deepfakes to trick smart voice assistants. An attacker can record the victim's voice, synthesize the voice and create a recording of some command to trick the assistant in order to harm the victim. The aim of this work is to design an experiment that will simulate attacks, performed by synthetic voice, on voice assistants and then evaluate their defensiveness. The conducted experiment confirms the initial hypothesis of the vulnerability of voice assistants to deepfake attacks and the results are very alarming with an overall success rate of 90% indicating insufficient defense of voice assistants and require the implementation of additional countermeasures to prevent the risk of misuse as the number of voice assistants in active use is rapidly increasing.
|
|
|
Cloud-Native Single Sign-On with OpenID Connect and Keycloak
Koval, Maksym ; Pavela, Jiří (oponent) ; Malinka, Kamil (vedoucí práce)
This thesis delves into the principles of OAuth 2.0 and OpenID Connect protocols and explains how they should be implemented in a microservice architecture. Two Angular web clients and two Spring Boot servers were developed as applications for the demonstration. The paper also explains how to use Keycloak as an identity provider for the above applications. The result is centralized authentication of all applications as well as implementation of Single Sign On mechanism in a cloud-native environment.
|
|
|
Usability of Post-quantum Cryptography in IoT
Kratochvíl, Jakub ; Perešíni, Martin (oponent) ; Malinka, Kamil (vedoucí práce)
This work investigates the usability of post-quantum cryptographic algorithms and their resource requirements on constrained devices. General parameters are measured to evaluate the usability of each algorithm on an ESP32 with an Xtensa LX6 chip. The second part of this work focuses on the network communication size of the TLS 1.3 protocol, which uses post-quantum alternatives. Both parts include a comparison with current cryptographic algorithms. The results mainly show an increase in the resource requirements for the post-quantum algorithms in both measurement parts. Post-quantum cryptography is currently usable on devices similar to the ESP32 but is problematic or even unusable on devices with lower resources.
|
host ::
RSS.